scholarly journals DEEP LEARNING IMPLEMENTATION FOR EMPLOYEE ATTENDANCE SYSTEM IN UNIVERSITAS PERTAMINA

2021 ◽  
Vol 11 (2) ◽  
pp. 462-468
Author(s):  
Meredita Susanty ◽  
Sahrul Sahrul ◽  
Erwin Setiawan ◽  
Herminarto Nugroho
Keyword(s):  
Human Resource ◽  
Position Angle ◽  
Training Data ◽  
Rfid Tags ◽  
Learning Approach ◽  
Rfid Tag ◽  
Manual Recording ◽  
Hidden Layer ◽  
Employee Attendance ◽  
A Company

Attendance recording with RFID tags scan, make human resource (HR) staff’s task more effective and efficient because it is saving time and effort in performing manual recording and recapitulation that must be performed by the HR staff in a company. However, the number of cases where employees forget to bring their identification cards, which has an RFID tag increases the workload of human resource staff. This study proposes a facial recognition prototype as an alternative way to record employee attendance. The model used in this study uses artificial neural networks that have more than one hidden layer and uses a supervised learning approach. The results of the study show that when a high-resolution image provided for the training data, the prototype able to make an accurate prediction. However, some further study is needed before replacing existing attendance recordings with face recognition to address several problems such as distance between camera and object and accessories that affect the essential features in a face like glasses, headscarves, and mask. Further research should find the maximum distance between the object(s) and the camera and the position (angle) of the object towards the camera.

scholarly journals Exploiting heterogeneity in operational neural networks by synaptic plasticity

2021 ◽  
Author(s):  
Serkan Kiranyaz ◽  
Junaid Malik ◽  
Habib Ben Abdallah ◽  
Turker Ince ◽  
Alexandros Iosifidis ◽  
...  
Keyword(s):  
Neural Networks ◽  
Synaptic Plasticity ◽  
Network Model ◽  
Neuron Model ◽  
Linear Operators ◽  
Training Data ◽  
Learning Performance ◽  
Minimal Network ◽  
Hidden Layer ◽  
Hidden Neurons

AbstractThe recently proposed network model, Operational Neural Networks (ONNs), can generalize the conventional Convolutional Neural Networks (CNNs) that are homogenous only with a linear neuron model. As a heterogenous network model, ONNs are based on a generalized neuron model that can encapsulate any set of non-linear operators to boost diversity and to learn highly complex and multi-modal functions or spaces with minimal network complexity and training data. However, the default search method to find optimal operators in ONNs, the so-called Greedy Iterative Search (GIS) method, usually takes several training sessions to find a single operator set per layer. This is not only computationally demanding, also the network heterogeneity is limited since the same set of operators will then be used for all neurons in each layer. To address this deficiency and exploit a superior level of heterogeneity, in this study the focus is drawn on searching the best-possible operator set(s) for the hidden neurons of the network based on the “Synaptic Plasticity” paradigm that poses the essential learning theory in biological neurons. During training, each operator set in the library can be evaluated by their synaptic plasticity level, ranked from the worst to the best, and an “elite” ONN can then be configured using the top-ranked operator sets found at each hidden layer. Experimental results over highly challenging problems demonstrate that the elite ONNs even with few neurons and layers can achieve a superior learning performance than GIS-based ONNs and as a result, the performance gap over the CNNs further widens.

scholarly journals A STUDY ON THE MAGNITUDE OF HUMAN RESOURCE IN SUN AND RANBAXY MERGER

2016 ◽  
Vol 10 (1) ◽  
pp. 29
Author(s):  
S Anjalidaisy ◽  
C Vijayabanu
Keyword(s):  
Mergers And Acquisitions ◽  
Product Development ◽  
Change Management ◽  
Employee Engagement ◽  
Human Resource ◽  
Generic Drug ◽  
Corporate Strategy ◽  
Drug Market ◽  
Pharmaceutical Sector ◽  
A Company

ABSTRACTSun Pharmaceutical is a trailblazer in Indian pharmaceutical sector, and one of the foremost competitors in the generic drug market sets its eye onRanbaxy. Sun pharmacy which was established in 1983 listed from 1994 has its upper hand in product development. Ranbaxy was incorporated in1973, and Daiichi Sankyo, a Japanese firm, got a controlling share from 2008. This amalgamation between Sun Pharmacy and Ranbaxy would getprofitable transaction for the former. The process of the coalition was a cloak and dagger affair until April 6, 2014. Before mergers and acquisitions,a company has to create an urgency call among the employees which will result in better understanding of the whole scenario. The aspects are abouthow financial motives and non-financial motives play a major role in mergers. This case deals with the human resource issues and complexities facedby the two players in the same business.Keywords: Merger, Acquisition, Change management, Human resource, Employee engagement, Corporate strategy.

scholarly journals Experimental Study on Inkjet-Printed Passive UHF RFID Tags on Versatile Paper-Based Substrates

2016 ◽  
Vol 2016 ◽  
pp. 1-8 ◽  
Author(s):  
Han He ◽  
Lauri Sydänheimo ◽  
Johanna Virkki ◽  
Leena Ukkonen
Keyword(s):  
Substrate Material ◽  
Optimal Number ◽  
Rfid Tags ◽  
Uhf Rfid ◽  
Rfid Tag ◽  
Passive Uhf Rfid ◽  
Wireless Applications ◽  
Efficient Manufacturing ◽  
Nanoparticle Ink ◽  
Pattern Resolution

We present the possibilities and challenges of passive UHF RFID tag antennas manufactured by inkjet printing silver nanoparticle ink on versatile paper-based substrates. The most efficient manufacturing parameters, such as the pattern resolution, were determined and the optimal number of printed layers was evaluated for each substrate material. Next, inkjet-printed passive UHF RFID tags were fabricated on each substrate with the optimized parameters and number of layers. According to our measurements, the tags on different paper substrates showed peak read ranges of 4–6.5 meters and the tags on different cardboard substrates exhibited peak read ranges of 2–6 meters. Based on their wireless performance, these inkjet-printed paper-based passive UHF RFID tags are sufficient for many future wireless applications and comparable to tags fabricated on more traditional substrates, such as polyimide.

scholarly journals Analysis of Company Human Capital Network Based on the Cellular Automation

2016 ◽  
Vol 11 (5) ◽  
pp. 244
Author(s):  
Zirong Zhuo ◽  
Zhiwei Cheng ◽  
Yangzhou Lai ◽  
Ziyue Chen
Keyword(s):  
Human Capital ◽  
Human Resources ◽  
Human Resource ◽  
Indicator System ◽  
Vacancy Rate ◽  
Resource Network ◽  
Cellular Automation ◽  
Human Cost ◽  
Value Model ◽  
A Company

In the age of knowledge economy, human resource is among the most important resources for enterprises, in that it forms the unique value of human resources which plays an indispensable role in the production and operating activities. Well managed human resources can effectively promote efficiency and thus create more social values. Therefore, it has aroused wide attention in academia. The thesis first establish the human capital value model and the human cost value model, based on which the thesis established the basic framework of enterprise human capital network. Then, simulation calculation from three aspects of human resource network were carried out with the cellular automation model. Firstly, we simulated the dynamic process of the change of personnel and got the evaluation model of the human cost in the future two years of a company, which can provide reference for company cost control. Secondly, the simulation mainly focused on checking whether under high staff churn rate, a company can still maintain certain number of employees. Thirdly, we simulated the healthy status of the human resource network under certain situations. Finally, We concluded that higher staff churn rate can lead to higher vacancy rate, which will lower the efficiency of companies .The thesis also explored with the model sensitivity analysis the benefit effect over human resource network by increasing recruits, indicating that increasing recruits can decrease the vacancy rate and improve the health status of the human capital network and based on the reality, we put forward the improvement direction of the model in indicator system aspect.

An Effective Solution to Regression Problem by RBF Neuron Network

2015 ◽  
Vol 6 (4) ◽  
pp. 57-74 ◽  
Author(s):  
Dang Thi Thu Hien ◽  
Hoang Xuan Huan ◽  
Le Xuan Minh Hoang
Keyword(s):  
Regression Function ◽  
Training Data ◽  
Neuron Network ◽  
Open Problems ◽  
Regression Problem ◽  
Rbf Network ◽  
Network Training ◽  
Hidden Layer ◽  
Definition Of ◽  
Selection Of

Radial Basis Function (RBF) neuron network is being applied widely in multivariate function regression. However, selection of neuron number for hidden layer and definition of suitable centre in order to produce a good regression network are still open problems which have been researched by many people. This article proposes to apply grid equally space nodes as the centre of hidden layer. Then, the authors use k-nearest neighbour method to define the value of regression function at the center and an interpolation RBF network training algorithm with equally spaced nodes to train the network. The experiments show the outstanding efficiency of regression function when the training data has Gauss white noise.

scholarly journals Unsupervised Deep Learning via Affinity Diffusion

2020 ◽  
Vol 34 (07) ◽  
pp. 11029-11036
Author(s):  
Jiabo Huang ◽  
Qi Dong ◽  
Shaogang Gong ◽  
Xiatian Zhu
Keyword(s):  
Deep Learning ◽  
State Of The Art ◽  
General Purpose ◽  
Training Data ◽  
Learning Approach ◽  
Model Learning ◽  
Feature Representations ◽  
Discriminative Feature ◽  
Training Samples ◽  
Unsupervised Deep Learning

Convolutional neural networks (CNNs) have achieved unprecedented success in a variety of computer vision tasks. However, they usually rely on supervised model learning with the need for massive labelled training data, limiting dramatically their usability and deployability in real-world scenarios without any labelling budget. In this work, we introduce a general-purpose unsupervised deep learning approach to deriving discriminative feature representations. It is based on self-discovering semantically consistent groups of unlabelled training samples with the same class concepts through a progressive affinity diffusion process. Extensive experiments on object image classification and clustering show the performance superiority of the proposed method over the state-of-the-art unsupervised learning models using six common image recognition benchmarks including MNIST, SVHN, STL10, CIFAR10, CIFAR100 and ImageNet.

scholarly journals Design of Nested H slot Passive UHF RFID Tag

2020 ◽  
Vol 10 (1) ◽  
pp. 346-349
Keyword(s):  
High Frequency ◽  
Microstrip Antenna ◽  
Rfid Tags ◽  
Uhf Rfid ◽  
Antenna Structure ◽  
Rfid Tag ◽  
Passive Uhf Rfid ◽  
Related Information ◽  
Distance Communication ◽  
Passive Rfid

RFID is a short distance communication system which comprises of a RFID tag, a RFID reader and a personal computer with desired software that can maintain the related information. These RFID tags can be of active or passive types. This paper focuses on design, simulation and fabrication of passive ultra-high frequency RFID tag (microchip and an antenna) which resonates at the frequency 866 MHz in the Industrial Scientific Medical Band. The nested H-slot inverted-F microstrip antenna structure is used for the design of passive RFID tag. It examines the specific tag geometry and its characteristics to optimize the PIFA antenna and in turn RFID tag’s performance.

scholarly journals Smart Roadways Ticketing System (SRTS) using RFID tags

2019 ◽  
Vol 8 (2) ◽  
pp. 4298-4301
Keyword(s):  
Rfid Tags ◽  
Card Holder ◽  
Rfid Tag ◽  
Tension Free ◽  
Transport Vehicle ◽  
Straightforward Approach

To provide a comfort, tension free, straightforward approach of traveling and conjointly to scale back the man power. SRTS involves the effective usage of RFID tags and Reed sensor to make ticketing better, through which the tag holds the identity of the card holder and Reed sensor, comprising a sensor and magnet to determine the distance travelled by the user. RFID Tag can be used by the user for just entering and leaving the bus. Depending on the distance which is travelled by the user, money will be deducted from the card well in advance. An object counter is placed adjacently to detect the number of persons entering the transport vehicle

Adaptive Framework for Collisions in RFID Tag Identification

2008 ◽  
Vol 07 (01) ◽  
pp. 9-14 ◽  
Author(s):  
Selwyn Piramuthu
Keyword(s):  
Supply Chain ◽  
Radio Frequency Identification ◽  
Rfid Tags ◽  
Tag Identification ◽  
Seamless Integration ◽  
Essential Information ◽  
Rfid Tag ◽  
Frequency Identification ◽  
Pass Through ◽  
Aloha Protocol

Radio Frequency Identification (RFID) is promising, as a technique, to enable tracking of essential information about objects as they pass through supply chains. Information thus tracked can be utilised to efficiently operate the supply chain. Effective management of the supply chain translates to huge competitive advantage for the firms involved. Among several issues that impede seamless integration of RFID tags in a supply chain, one of the problems encountered while reading RFID tags is that of collision, which occurs when multiple tags transmit data to the same receiver slot. Data loss due to collision necessitates re-transmission of lost data. We consider this problem when Framed Slotted ALOHA protocol is used. Using machine learning, we adaptively configure the number of slots per frame to reduce the number of collisions while improving throughput.

Embedded RFID Solutions

2012 ◽  
pp. 1873-1884
Author(s):  
Álvaro M. Sampaio ◽  
António J. Pontes ◽  
Ricardo Simões
Keyword(s):  
New Products ◽  
User Interaction ◽  
Consumer Products ◽  
Rfid Tags ◽  
Rfid Technology ◽  
Rfid Tag ◽  
Production Distribution ◽  
Innovative Solutions ◽  
New Challenges

Full traceability of products is extremely difficult, although it has been sought after for as long as production, distribution and sales chains exist. Electronic traceability methods, such as RFID technology, have been proposed as a possible solution to this problem. In the specific case of RFID, the number of applications that promote innovative solutions in retail and other areas has been continuous growing. However, RFID tags are mostly placed externally on a surface of products or their packages. This is appropriate for logistics, but not for other applications, such as those involving user interaction. In those, not only is the placement of the RFID tag more complex, but it is also necessary that the tag is not visible or not directly accessible, to prevent accidental damage and intentional abuse. This certainly imposes challenges to manufacturing, but mainly creates new challenges to the development of new products and re-design of existing ones. This chapter presents some insights and what we consider to be the two main approaches to incorporating RFID technology into consumer products.

Sign in / Sign up

Export Citation Format

Share Document